Grace Zhang

I am a third-year PhD student at USC, advised by Professor Joseph J. Lim. Prior to joining USC, I received my BS in EECS at UC Berkeley where I did research with Professor Sergey Levine .

Email  /  GitHub  /  Google Scholar  

Research

I am interested in efficient robot learning methods for automating complex long horizon tasks. Specifically, my research focuses on the generalization of learned policies to new environments as well as the use of prior knowledge and skills to build hierarchical policies.

Policy Transfer across Visual and Dynamics Domain Gaps via Iterative Grounding

MCP: Learning Composable Hierarchical Control with Multiplicative Compositional Policies

Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning

Teaching

EECS 127: Optimization Models in Engineering

EECS 16A: Designing Information Devices and Systems I

Website template from Jon Barron and Leonid Keselman